Vehicle body curved surface simulation prediction method and system based on machine learning

Abstract

The invention relates to a vehicle body curved surface simulation prediction method and system based on machine learning, and the method comprises the steps: determining a plurality of input parameters and output parameters of vehicle body curved surface simulation, the input parameters at least comprise a vehicle body section shape and material thickness, and the output parameters at least comprise bending frequency, torsion frequency, bending rigidity and torsion rigidity; constructing a data set by taking the plurality of input parameters and the plurality of output parameters as samples and labels respectively, and training a machine learning model by using the data set to obtain a trained machine learning model; and inputting a plurality of input parameters of the to-be-simulated vehicle body curved surface into the trained machine learning model to obtain a plurality of predicted output parameters of the to-be-simulated vehicle body curved surface. According to the method, the parameterized model is combined with machine learning, and the multi-dimensional output parameters of the curved surface of the vehicle body are predicted, so that the simulation accuracy and the automation degree are improved.

Description

technical field [0001] The invention belongs to the technical field of vehicle manufacturing and simulated driving, and in particular relates to a method and system for simulation and prediction of body surfaces based on machine learning. Background technique [0002] The simulation technology of traditional vehicles requires a lot of time and computing resources. If the optimized structure needs to be changed, the simulation calculation needs to be resubmitted, which is time-consuming and labor-intensive. Later, the introduction of the parameterized model greatly improves the optimization efficiency. It is possible to set parameters for sensitive structures through experience. , and then simulate by changing the parameters to obtain a large number of output results, and then complete the response surface method based on these results to establish a continuous variable surface model, the purpose is to predict the output results without simulation, but the problem of this meth...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem that the response surface method establishes a continuous variable surface model that is highly dependent on labor and is time-consuming and laborious, and improves the accuracy of the continuous variable surface model, a method for simulation prediction of a vehicle body surface based on machine learning is provided in the first aspect of the present invention, including: Determine a plurality of input parameters and output parameters of the surface simulation of the vehicle body, the input parameters at least include the cross-sectional shape and material thickness of the vehicle body, and the output parameters at least include bending frequency, torsional frequency, bending stiffness and torsional stiffness; Parameters, the multiple output parameters are samples and labels respectively, construct a data set, and use the data set to train a machine learning model to obtain a machine learning model that has been trained; input multiple input parameters of the curved surface of the car body to be simulated into The trained machine learning model can obtain multiple predicted output parameters of the surface to be simulated

Images